administrator/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-07-15 08:21:16 +03:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Fallback and try llama-swap format

Browse Source
This commit is contained in:
Nicolas Mowen 2026-04-03 15:32:54 -06:00
parent bae30211d2
commit 78b22d722e
1 changed files with 19 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
frigate/genai/llama_cpp.py
View File

@ -101,15 +101,26 @@ class LlamaCppClient(GenAIClient):
e, e,
) )
# Query /props for context size, modalities, and tool support # Query /props for context size, modalities, and tool support.
# The standard /props?model=<name> endpoint works with llama-server.
# If it fails, try the llama-swap per-model passthrough endpoint which
# returns props for a specific model without requiring it to be loaded.
try: try:
response = requests.get( try:
f"{base_url}/props", response = requests.get(
params={"model": configured_model}, f"{base_url}/props",
timeout=10, params={"model": configured_model},
) timeout=10,
response.raise_for_status() )
props = response.json() response.raise_for_status()
props = response.json()
except Exception:
response = requests.get(
f"{base_url}/upstream/{configured_model}/props",
timeout=10,
)
response.raise_for_status()
props = response.json()
# Context size from server runtime config # Context size from server runtime config
default_settings = props.get("default_generation_settings", {}) default_settings = props.get("default_generation_settings", {})